Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 7380
    Prev
    Next
    INDEX
    Explanations

    no followed by a concept

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ка
    3.24
    হীন
    3.15
    ি
    3.07
     डाइऑक्साइड
    2.94
    За
    2.90
    v
    2.89
    p
    2.82
    ^{
    2.79
    ped
    2.74
    män
    2.70
    POSITIVE LOGITS
     obstante
    3.42
     entanto
    2.82
     eens
    2.80
    httpRequest
    2.65
    жные
    2.63
    bitwise
    2.59
     mutually
    2.50
     longer
    2.48
     ifs
    2.47
    ções
    2.44
    Activations Density 0.128%

    No Known Activations